GIV-CXR: Densely Grounded, Visually Interpretable Chest X-ray Question Answering Dataset
A grounded chest X-ray visual question answering benchmark linking answers with interpretable visual evidence across anatomy and findings.














We build and study learning systems for language, vision, graphs, and human-centered AI at Mahindra University.
Featured papers, project pages, campus visits, workshops, and student highlights moving together as one lab feed.
A grounded chest X-ray visual question answering benchmark linking answers with interpretable visual evidence across anatomy and findings.
Introduces a BCI-aware perceptual-semantic coherence framework for EEG-to-image reconstruction evaluation using VLM-routed annotations and human validation across 6,885 image pairs from ATM, ENIGMA, BrainVis, and DreamDiffusion.
A grounded chest X-ray visual question answering benchmark linking answers with interpretable visual evidence across anatomy and findings.
Introduces a BCI-aware perceptual-semantic coherence framework for EEG-to-image reconstruction evaluation using VLM-routed annotations and human validation across 6,885 image pairs from ATM, ENIGMA, BrainVis, and DreamDiffusion.

Lab moment
Mentorship visit at the Regional Mentoring Session on Innovation (Boot Camp, Day 2) for PM SHRI school teachers and students.

Lab moment
ACM India ARCS is an annual symposium for PhD researchers. The 2026 edition ran Feb 11-13 at IIT Hyderabad with talks, posters, and mentoring sessions.

Lab moment
Highlights from the IIIT Hyderabad visit and collaborations.

Lab moment
Mentorship visit at the Regional Mentoring Session on Innovation (Boot Camp, Day 2) for PM SHRI school teachers and students.

Lab moment
ACM India ARCS is an annual symposium for PhD researchers. The 2026 edition ran Feb 11-13 at IIT Hyderabad with talks, posters, and mentoring sessions.

Lab moment
Highlights from the IIIT Hyderabad visit and collaborations.
Materials from recent semesters, organized by term.
View all teachingsPeople behind the work
Faculty, researchers, interns, and students building VLaNC Lab research across vision, language, and cognition.